14 citations · 34 across the 14 of their papers we have counts for
14 papers · 1 filter
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Zorik Gekhman, Roee Aharoni, Eran Ofek +3
While reasoning in LLMs plays a natural role in math, code generation, and multi-hop factual questions, its effect on simple, single-hop factual questions remains unclear. Such que…
Evaluating Alignment of Behavioral Dispositions in LLMs
Amir Taubenfeld, Zorik Gekhman, Lior Nezry +8
As people turn to LLMs for social advice, understanding their behavior in such contexts becomes essential. In this work, we focus on behavioral dispositions: the underlying tendenc…
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
Nitay Calderon, Eyal Ben-David, Zorik Gekhman +2
Standard factuality evaluations of LLMs treat all errors alike, obscuring whether failures arise from missing knowledge (empty shelves) or from limited access to encoded facts (los…
HACK: Hallucinations Along Certainty and Knowledge Axes
Adi Simhi, Jonathan Herzig, Itay Itzhak +7
Hallucinations in LLMs present a critical barrier to their reliable usage. Existing research usually categorizes hallucination by their external properties rather than by the LLMs'…
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs
Yehonatan Peisakhovsky, Zorik Gekhman, Yosi Mass +2
Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hal…
Confidence Improves Self-Consistency in LLMs
Amir Taubenfeld, Tom Sheffer, Eran Ofek +4
Self-consistency decoding enhances LLMs' performance on reasoning tasks by sampling diverse reasoning paths and selecting the most frequent answer. However, it is computationally e…
LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
Hadas Orgad, Michael Toker, Zorik Gekhman +4
Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failures, collectively referred to as "hallucinations". Recent studies have…
Can LLMs Learn Macroeconomic Narratives from Social Media?
Almog Gueta, Amir Feder, Zorik Gekhman +2
This study empirically tests the hypothesis, which posits that narratives (ideas that are spread virally and affect public beliefs) can influence eco…
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
Zorik Gekhman, Gal Yona, Roee Aharoni +4
When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured th…
Using Text Injection to Improve Recognition of Personal Identifiers in Speech
Yochai Blau, Rohan Agrawal, Lior Madmony +7
Accurate recognition of specific categories, such as persons' names, dates or other identifiers is critical in many Automatic Speech Recognition (ASR) applications. As these catego…
Measuring the Robustness of NLP Models to Domain Shifts
Nitay Calderon, Naveh Porat, Eyal Ben-David +5
Existing research on Domain Robustness (DR) suffers from disparate setups, limited task variety, and scarce research on recent capabilities such as in-context learning. Furthermore…
TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models
Zorik Gekhman, Jonathan Herzig, Roee Aharoni +2
Factual consistency evaluation is often conducted using Natural Language Inference (NLI) models, yet these models exhibit limited success in evaluating summaries. Previous work imp…
On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method
Zorik Gekhman, Nadav Oved, Orgad Keller +2
Most works on modeling the conversation history in Conversational Question Answering (CQA) report a single main result on a common CQA benchmark. While existing models show impress…
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
Zorik Gekhman, Dina Zverinski, Jonathan Mallinson +1
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually us…